Skip to main content
Glama

demo_learn

Converts a screen recording into a draft workflow skill by extracting frames, reading on-screen text with OCR or a local vision model, and turning unclear steps into questions to answer.

Instructions

Learn a workflow from a screen recording and turn it into a skill DRAFT.

Frames are extracted (ffmpeg/opencv if installed), the screen text is read with OCR - or, when no OCR engine is installed, described by a LOCAL vision model - changed frames become steps, and the unclear parts become questions for you. The result is a draft, not a verified skill - answer the questions first.

video_path may also be a FOLDER of images (PNG/JPG): extract the frames yourself and hand the folder over - no decoder needed.

Blocked honestly when there is neither a decoder (or a folder), nor an OCR engine, nor a local vision model.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "video_path": "<video_path>"
    },
    "name": "demo_learn"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
max_framesNo
video_pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the internal pipeline (frame extraction via ffmpeg/opencv, OCR, fallback to a local vision model), the honest prerequisite/blocking condition when none of those are available, and that output is an unverified draft requiring follow-up answers. It does not mention runtime cost or sensitivity of screen content, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action in sentence one, followed by mechanics, input alternatives, and failure behavior in a sensible order. A few clauses restate the draft/verify idea twice, but there is no filler paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an unannotated, schema-poor, output-schema-less tool of this complexity, the description covers prerequisites, mechanics, and failure modes well. Gaps remain on what the draft artifact actually contains and where it lands, and on the undocumented 'name' and 'max_frames' parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it only partially does: video_path is richly explained (file or folder of PNG/JPG images, no decoder needed) and max_frames is loosely implied by the frame-extraction narrative, but the 'name' parameter and the 60-frame default are never addressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb ('learn') and resource ('a workflow from a screen recording') and states the concrete artifact produced ('a skill DRAFT'). It is clear what the tool does, though it never names the sibling tools (e.g. body_skill_save, body_skill_replay) that would sharpen the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than stated: the reader learns to 'answer the questions first' and that a folder of images may be passed instead of a video, which implies when each input form applies. There is no explicit when-to-use/when-not-to-use guidance relative to the skill-save or lessons siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.